OpenAI gives Codex reusable cloud environments that work across devices
OpenAI is expanding Codex with reusable cloud development environments, a revamped CLI with voice controls, new code review tools and a security-focused product for scanning repositories and preparing fixes.
OpenAI has enhanced its software engineering agent Codex, enabling it to work beyond a developer's laptop with the introduction of reusable cloud development environments. These environments, announced during OpenAI's Dev Day, can be accessed from any device, making them more persistent and configurable. This update allows tasks to begin more quickly and provides teams with a shared workspace, complete with approved settings and permissions.
Codex users can now operate these environments from various devices, including computers, phones, or in the cloud. The refreshed Codex Command-Line Interface (CLI) enables developers to start and direct tasks using voice commands. A new "/agents" view aims to simplify the delegation of work and tracking of multiple tasks simultaneously.
Additional improvements include enhancements to common tasks, such as editing prompts, resuming sessions, and using worktrees. The company is also introducing a "cleaner" terminal user interface to improve readability in longer sessions. Codex can be integrated into a new code review experience within the ChatGPT desktop app, where users can read summaries, explore code changes, and receive potential issue alerts before sharing feedback on GitHub or GitLab pull requests.
Codex can also perform initial code reviews asynchronously, allowing users to step away from their computers.
Security features have been expanded with the launch of Codex Security Cloud, a toolset designed to help developers secure their infrastructure. This toolset enables developers to scan GitHub repositories on-demand, on a regular schedule, or whenever new commits arrive. Codex will investigate findings, remove duplicates, and prepare fixes in the cloud, even when the user is inactive.
OpenAI has also announced several API updates. The new Decisions API facilitates real-time decision-making by answering user-defined questions with predefined answers using Luna. An updated version of the Agents API now supports computer use and allows the creation of OpenAI agents that run entirely on AWS, utilizing Amazon's Bedrock Managed Agents.
Written by urgent.news from TechCrunch's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
